Authors: Ali Mehrban, Pegah Ahadian

Published on: January 08, 2024

Impact Score: 8.07

Arxiv code: Arxiv:2401.05441

Summary

• What is new: Utilizes ANFIS for predicting cryptocurrency prices up to seven days in advance using a novel combination of hybrid and backpropagation algorithms alongside various clustering techniques.
• Why this is important: The difficulty in forecasting cryptocurrency prices accurately due to their volatile nature.
• What the research proposes: An architecture based on ANFIS, employing hybrid learning and different clustering algorithms to improve prediction accuracy.
• Results: The architecture outperforms previous models, showing better statistical evaluation in short-term cryptocurrency price prediction.

Technical Details

Technological frameworks used: Adaptive Network Based Fuzzy Inference System (ANFIS)

Models used: Hybrid and backpropagation algorithms, grid partition, subtractive clustering, Fuzzy C-means clustering

Data used: Historical data of BTC, ETH, BTC.D, and ETH.D.

Potential Impact

Cryptocurrency exchanges, investment firms, fintech startups focusing on crypto trading tools.

Want to implement this idea in a business?

We have generated a startup concept here: CryptoPredictive Analytics.